CA3020995C - Amelioration de la precision d'une reconnaissance optique de caracteres (ocr) grace a la combinaison de resultats obtenus sur des trames video - Google Patents

Amelioration de la precision d'une reconnaissance optique de caracteres (ocr) grace a la combinaison de resultats obtenus sur des trames video Download PDF

Info

Publication number
CA3020995C
CA3020995C CA3020995A CA3020995A CA3020995C CA 3020995 C CA3020995 C CA 3020995C CA 3020995 A CA3020995 A CA 3020995A CA 3020995 A CA3020995 A CA 3020995A CA 3020995 C CA3020995 C CA 3020995C
Authority
CA
Canada
Prior art keywords
document
data
text data
extracted
confidence level
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CA3020995A
Other languages
English (en)
Other versions
CA3020995A1 (fr
Inventor
Vijay Yellapragada
Peijun Chiang
Sreeneel K. Maddika
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Intuit Inc
Original Assignee
Intuit Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Intuit Inc filed Critical Intuit Inc
Publication of CA3020995A1 publication Critical patent/CA3020995A1/fr
Application granted granted Critical
Publication of CA3020995C publication Critical patent/CA3020995C/fr
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/12—Accounting
    • G06Q40/123—Tax preparation or submission
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition
    • G06V30/41—Analysis of document content
    • G06V30/416—Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30176—Document

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Technology Law (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Character Discrimination (AREA)
  • Character Input (AREA)

Abstract

La présente invention concerne la reconnaissance optique de caractères à l'aide d'une vidéo capturée. Selon un mode de réalisation, le dispositif exécute les opérations consistant à : extraire, au moyen d'une première image dans un flux d'images décrivant un document, des données de texte dans une partie du document représentée sur la première image ; déterminer un premier niveau de confiance relatif à une précision des données de texte extraites ; et si le premier niveau de confiance correspond à une valeur de seuil, sauvegarder les données de texte extraites à titre de contenu reconnu du document source ; ou dans le cas contraire, extraire les données de texte de la partie du document représentée sur une ou plusieurs secondes images dans le flux ; et déterminer un second niveau de confiance relatif aux données de texte extraites de chaque seconde image jusqu'à l'identification d'une des secondes images dans laquelle le second niveau de confiance associé aux données de texte extraites de la seconde image identifiée correspond à la valeur de seuil.
CA3020995A 2016-07-25 2017-05-04 Amelioration de la precision d'une reconnaissance optique de caracteres (ocr) grace a la combinaison de resultats obtenus sur des trames video Active CA3020995C (fr)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US15/218,907 2016-07-25
US15/218,907 US10210384B2 (en) 2016-07-25 2016-07-25 Optical character recognition (OCR) accuracy by combining results across video frames
PCT/US2017/030995 WO2018022166A1 (fr) 2016-07-25 2017-05-04 Amélioration de la précision d'une reconnaissance optique de caractères (ocr) grâce à la combinaison de résultats obtenus sur des trames vidéo

Publications (2)

Publication Number Publication Date
CA3020995A1 CA3020995A1 (fr) 2018-02-01
CA3020995C true CA3020995C (fr) 2020-01-14

Family

ID=58765909

Family Applications (1)

Application Number Title Priority Date Filing Date
CA3020995A Active CA3020995C (fr) 2016-07-25 2017-05-04 Amelioration de la precision d'une reconnaissance optique de caracteres (ocr) grace a la combinaison de resultats obtenus sur des trames video

Country Status (5)

Country Link
US (2) US10210384B2 (fr)
EP (1) EP3440591B1 (fr)
AU (1) AU2017301369B2 (fr)
CA (1) CA3020995C (fr)
WO (1) WO2018022166A1 (fr)

Families Citing this family (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8744119B2 (en) * 2011-01-12 2014-06-03 Gary S. Shuster Graphic data alteration to enhance online privacy
WO2017223335A1 (fr) * 2016-06-23 2017-12-28 Capital One Services, Llc Systèmes et procédés de reconnaissance d'objet automatisé
US10255516B1 (en) * 2016-08-29 2019-04-09 State Farm Mutual Automobile Insurance Company Systems and methods for using image analysis to automatically determine vehicle information
US10223584B2 (en) * 2016-11-01 2019-03-05 Ncr Corporation Document detection
US10623569B2 (en) * 2017-06-08 2020-04-14 Avaya Inc. Document detection and analysis-based routing
US10621279B2 (en) * 2017-11-27 2020-04-14 Adobe Inc. Conversion quality evaluation for digitized forms
JP6791191B2 (ja) * 2018-04-02 2020-11-25 日本電気株式会社 画像処理装置、画像処理方法およびプログラム
JP6874729B2 (ja) * 2018-04-02 2021-05-19 日本電気株式会社 画像処理装置、画像処理方法およびプログラム
US11093784B2 (en) * 2018-11-08 2021-08-17 Rapid Financial Services, LLC System for locating, interpreting and extracting data from documents
US10824917B2 (en) 2018-12-03 2020-11-03 Bank Of America Corporation Transformation of electronic documents by low-resolution intelligent up-sampling
US10735615B1 (en) 2019-03-15 2020-08-04 Ricoh Company, Ltd. Approach for cloud EMR communication via a content parsing engine
US10402641B1 (en) * 2019-03-19 2019-09-03 Capital One Services, Llc Platform for document classification
US11520827B2 (en) * 2019-06-14 2022-12-06 Dell Products L.P. Converting unlabeled data into labeled data
US10803057B1 (en) * 2019-08-23 2020-10-13 Capital One Services, Llc Utilizing regular expression embeddings for named entity recognition systems
US11861523B2 (en) 2019-09-30 2024-01-02 Ricoh Company, Ltd. Approach for cloud EMR communication via a content parsing engine and a storage service
US10956106B1 (en) * 2019-10-30 2021-03-23 Xerox Corporation Methods and systems enabling a user to customize content for printing
US11227153B2 (en) 2019-12-11 2022-01-18 Optum Technology, Inc. Automated systems and methods for identifying fields and regions of interest within a document image
US11210507B2 (en) * 2019-12-11 2021-12-28 Optum Technology, Inc. Automated systems and methods for identifying fields and regions of interest within a document image
CN111723790A (zh) * 2020-06-11 2020-09-29 腾讯科技（深圳）有限公司 视频字幕的筛选方法、装置、设备及存储介质
US11461541B2 (en) * 2020-06-24 2022-10-04 Kyndryl, Inc. Interactive validation of annotated documents
US11720961B2 (en) * 2020-08-31 2023-08-08 Softworks Ai, Llc Validation method and system to improve data accuracy
CN112434668A (zh) * 2020-12-14 2021-03-02 北京一起教育科技有限责任公司 一种评价整洁度的方法、装置及电子设备
US20220351088A1 (en) * 2021-04-30 2022-11-03 Intuit Inc. Machine learning model-agnostic confidence calibration system and method
US20230023431A1 (en) * 2021-07-26 2023-01-26 Lenovo (Singapore) Pte. Ltd. Adjusting resolution of video stream based on optical character recognition
CN113780285B (zh) * 2021-09-27 2024-03-15 常州市公共资源交易中心 证照分析方法、装置和存储介质
US12026173B1 (en) 2023-08-14 2024-07-02 Bank Of America Corporation System and method for extraction management

Family Cites Families (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3913985B2 (ja) * 1999-04-14 2007-05-09 富士通株式会社 文書画像中の基本成分に基づく文字列抽出装置および方法
US7280684B2 (en) * 2003-07-30 2007-10-09 International Business Machines Corporation Method and system for ongoing performance monitoring of a character recognition system
EP1787289B1 (fr) * 2004-07-30 2018-01-10 Dictaphone Corporation Dispositif et procédé de détermination de la fiabilité des transcriptions des rapports
US8600989B2 (en) 2004-10-01 2013-12-03 Ricoh Co., Ltd. Method and system for image matching in a mixed media environment
US7400776B2 (en) 2005-01-10 2008-07-15 International Business Machines Corporation Visual enhancement for reduction of visual noise in a text field
US8553968B1 (en) * 2005-02-18 2013-10-08 Western Digital Technologies, Inc. Using optical character recognition augmented by an error correction code to detect serial numbers written on a wafer
GB2466597B (en) * 2007-09-20 2013-02-20 Kyos Systems Inc Method and apparatus for editing large quantities of data extracted from documents
US8983170B2 (en) * 2008-01-18 2015-03-17 Mitek Systems, Inc. Systems and methods for developing and verifying image processing standards for mobile deposit
KR20100064533A (ko) 2008-12-05 2010-06-15 삼성전자주식회사 카메라를 이용한 문자 크기 자동 조절 장치 및 방법
US20120029918A1 (en) * 2009-09-21 2012-02-02 Walter Bachtiger Systems and methods for recording, searching, and sharing spoken content in media files
US10002192B2 (en) * 2009-09-21 2018-06-19 Voicebase, Inc. Systems and methods for organizing and analyzing audio content derived from media files
US8600152B2 (en) * 2009-10-26 2013-12-03 Ancestry.Com Operations Inc. Devices, systems and methods for transcription suggestions and completions
US8515185B2 (en) 2009-11-25 2013-08-20 Google Inc. On-screen guideline-based selective text recognition
US9400790B2 (en) * 2009-12-09 2016-07-26 At&T Intellectual Property I, L.P. Methods and systems for customized content services with unified messaging systems
US8675923B2 (en) 2010-07-21 2014-03-18 Intuit Inc. Providing feedback about an image of a financial document
CN102890783B (zh) * 2011-07-20 2015-07-29 富士通株式会社 识别图像块中文字的方向的方法和装置
CN102890784B (zh) * 2011-07-20 2016-03-30 富士通株式会社 识别图像块中文字的方向的方法和装置
US9317764B2 (en) 2012-12-13 2016-04-19 Qualcomm Incorporated Text image quality based feedback for improving OCR
US9008428B2 (en) * 2013-01-28 2015-04-14 International Business Machines Corporation Efficient verification or disambiguation of character recognition results
US9305245B2 (en) 2013-05-07 2016-04-05 Xerox Corporation Methods and systems for evaluating handwritten documents
US8947745B2 (en) * 2013-07-03 2015-02-03 Symbol Technologies, Inc. Apparatus and method for scanning and decoding information in an identified location in a document
US20150120563A1 (en) 2013-10-29 2015-04-30 Bank Of America Corporation Check data lift for ach transactions
US9424524B2 (en) * 2013-12-02 2016-08-23 Qbase, LLC Extracting facts from unstructured text
US9292739B1 (en) * 2013-12-12 2016-03-22 A9.Com, Inc. Automated recognition of text utilizing multiple images
US9305227B1 (en) * 2013-12-23 2016-04-05 Amazon Technologies, Inc. Hybrid optical character recognition
EP3132381A4 (fr) 2014-04-15 2017-06-28 Kofax, Inc. Extension d'entrée/sortie (e/s) optique intelligente pour flux de tâches dépendant du contexte
WO2016149918A1 (fr) * 2015-03-25 2016-09-29 北京旷视科技有限公司 Détermination d'une position géographique d'un utilisateur

Also Published As

Publication number Publication date
EP3440591B1 (fr) 2022-10-12
US10210384B2 (en) 2019-02-19
AU2017301369B2 (en) 2019-09-12
WO2018022166A1 (fr) 2018-02-01
CA3020995A1 (fr) 2018-02-01
AU2017301369A1 (en) 2018-10-11
US20180025222A1 (en) 2018-01-25
EP3440591A1 (fr) 2019-02-13
US10558856B1 (en) 2020-02-11

Similar Documents

Publication Publication Date Title
CA3020995C (fr) Amelioration de la precision d'une reconnaissance optique de caracteres (ocr) grace a la combinaison de resultats obtenus sur des trames video
AU2020200058B2 (en) Image quality assessment and improvement for performing optical character recognition
US9639900B2 (en) Systems and methods for tax data capture and use
JP5509753B2 (ja) 認識結果を生成するためのシステム及び方法
AU2017302248A1 (en) Label and field identification without optical character recognition (OCR)
US10339373B1 (en) Optical character recognition utilizing hashed templates
CA3052248C (fr) Detection d'orientation de documents textuels alimentee par une camera en direct
US20220405499A1 (en) Method and system for extracting information from a document
US10229315B2 (en) Identification of duplicate copies of a form in a document

Legal Events

Date Code Title Description
EEER Examination request

Effective date: 20181012